Step 5 Preview API pricing
Updated
4 providers tie for the cheapest standard price for Step 5 Preview on the 3:1 blend; Featherless charges USD 1 per 1M input tokens and USD 2.70 per 1M output tokens. The median across 4 standard prices is USD 1 / USD 2.70. Every price is read from the provider's own pricing page, checked 2026-11-15.
Does StepFun sell Step 5 Preview directly?
StepFun publishes no price for Step 5 Preview on its own API that we could find, so this page compares hosts only.
Step 5 Preview price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 0% above the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Featherless tied cheapeststepfun-ai/Step-5-PreviewNotes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $1 / CACHED $0.1 / OUTPUT $2.7” | USD 1 | USD 0.10 | USD 2.70 | USD 1.425 | 262,144 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | GMI Cloud tied cheapeststepfun-ai/Step-5-PreviewNotes and source quote“Price (per 1M tokens) Input $1.00 Output $2.70 Cache Read $0.10 Cache Write -” | USD 1 | USD 0.10 | USD 2.70 | USD 1.425 | 1,048,576 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | Hyperbolic tied cheapeststep-5-previewNotes and source quoteContext shown on page as "1M" (rounded); stored as the decimal value. “Step 5 Preview step-5-preview StepFun · 1M context · Text $1.00 $2.70 $0.10” | USD 1 | USD 0.10 | USD 2.70 | USD 1.425 | 1,000,000 | not stated | Hyperbolic page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Novita AI tied cheapeststepfun/step-5-previewNotes and source quote“Step 5 Preview 977K $1 /Mt · Cache Read $0.1 /Mt $2.7 /Mt” | USD 1 | USD 0.10 | USD 2.70 | USD 1.425 | 1,000,000 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Step 5 Preview cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Featherless | USD 90.00 | USD 215.70 | USD 666.00 |
| GMI Cloud | USD 90.00 | USD 215.70 | USD 666.00 |
| Hyperbolic | USD 90.00 | USD 215.70 | USD 666.00 |
| Novita AI | USD 90.00 | USD 215.70 | USD 666.00 |
For the support chatbot, the cheapest price (Featherless and 3 others, tied, USD 90.00 a month) saves USD 0 against the median (USD 90.00). For the coding agent the gap is USD 0 a month.
Which Step 5 Preview provider is cheapest for your traffic?
All 4 providers charge the same standard price, USD 1 input and USD 2.70 output per 1M tokens, so the per-token price does not decide between them: compare the cache and context lines below.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| Featherless | USD 1.425 cheapest | USD 1.088 cheapest | USD 0.8175 cheapest |
| GMI Cloud | USD 1.425 cheapest | USD 1.088 cheapest | USD 0.8175 cheapest |
| Hyperbolic | USD 1.425 cheapest | USD 1.088 cheapest | USD 0.8175 cheapest |
| Novita AI | USD 1.425 cheapest | USD 1.088 cheapest | USD 0.8175 cheapest |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
All 4 providers publish a cached-input price below the input price: Featherless (90% off), GMI Cloud (90% off), Hyperbolic (90% off), Novita AI (90% off).
Context windows differ: 1,048,576 tokens at GMI Cloud; 1,000,000 tokens at Hyperbolic and Novita AI; 262,144 tokens at Featherless. The cheapest row is not always the one that fits a long prompt.
Estimate your own bill
- LLM API cost calculator with Step 5 Preview preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Step 5 Preview compare with other StepFun models?
The StepFun models whose cheapest standard price is closest to Step 5 Preview's (USD 1.425 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Step 3.7 Flash | USD 0.20 | USD 1.15 | 262,144 | 3 |
| Step-3.5-Flash | USD 0.10 | USD 0.30 | 262,144 | 2 |
Priced closest from other makers: Command A+ (Cohere, USD 1.40) · GLM 5.1 (Z.ai, USD 1.40) · Gemini 3.6 Flash (Google, USD 1.50).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Step 5 Preview API cost per token?
From USD 1 per 1M input tokens (USD 0.000001 per token) and USD 2.70 per 1M output tokens (USD 0.0000027 per token) at the cheapest standard price. The median of 4 standard prices is USD 1 input and USD 2.70 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Step 5 Preview?
4 providers are tied for the cheapest: Featherless, GMI Cloud, Hyperbolic and Novita AI, each USD 1.425 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 1 (Featherless and 3 others, tied); for output alone, USD 2.70 (Featherless and 3 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does StepFun sell Step 5 Preview on its own API?
StepFun publishes no price for Step 5 Preview on its own API that we could find, so there is no maker price to compare. The cheapest host is Featherless at USD 1 / USD 2.70 per 1M tokens.
Does Step 5 Preview have cached input pricing?
All 4 standard prices include one. The lowest is USD 0.10 per 1M at Featherless; the median is USD 0.10. Providers without one bill cached input at the input price. What cached input means.
What is the Step 5 Preview context window?
Up to 1,048,576 tokens. 3 standard prices come with less, down to 262,144 tokens (Featherless, Hyperbolic and Novita AI). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Step 5 Preview?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 666.00 a month at Featherless, USD 666.00 at the median price and USD 666.00 at Novita AI. Try your own numbers.
Is Step 5 Preview free to use through an API?
No provider in our data lists a free price for Step 5 Preview as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.